d61e15cf84
weboob.tools.browser -> weboob.deprecated.browser weboob.tools.parsers -> weboob.deprecated.browser.parsers weboob.tools.mech -> weboob.deprecated.mech weboob.browser2 -> weboob.browser weboob.core.exceptions -> weboob.exceptions Also, the new tree for browser2 is: weboob.browser: import weboob.browser.browsers.* and weboob.browser.url.* weboob.browser.browsers: all browsers (including PagesBrowser and LoginBrowser) weboob.browser.url: the URL class weboob.browser.profiles: all Profile classes weboob.browser.sessions: WeboobSession and FuturesSession weboob.browser.cookies: that's a cookies thing weboob.browser.pages: all Page and derivated classes, and Form class weboob.browser.exceptions: specific browser exceptions weboob.browser.elements: AbstractElement classes, and 'method' decorator weboob.browser.filters.*: all filters
63 lines
1.7 KiB
Python
63 lines
1.7 KiB
Python
# -*- coding: utf-8 -*-
|
|
|
|
# Copyright(C) 2010-2011 Romain Bignon
|
|
#
|
|
# This file is part of weboob.
|
|
#
|
|
# weboob is free software: you can redistribute it and/or modify
|
|
# it under the terms of the GNU Affero General Public License as published by
|
|
# the Free Software Foundation, either version 3 of the License, or
|
|
# (at your option) any later version.
|
|
#
|
|
# weboob is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# GNU Affero General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU Affero General Public License
|
|
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
|
|
import re
|
|
|
|
|
|
__all__ = ['IParser', 'RawParser']
|
|
|
|
|
|
class IParser(object):
|
|
def parse(self, data, encoding=None):
|
|
"""
|
|
Parse a HTML document with a specific encoding to get a tree.
|
|
|
|
@param data [str] HTML document
|
|
@param encoding [str] encoding to use
|
|
@return an object with the structured document
|
|
"""
|
|
raise NotImplementedError()
|
|
|
|
def tostring(self, elem):
|
|
"""
|
|
Get HTML string from an element.
|
|
"""
|
|
raise NotImplementedError()
|
|
|
|
def tocleanstring(self, elem):
|
|
"""
|
|
Get a clean string from an element.
|
|
"""
|
|
return self.strip(self.tostring(elem))
|
|
|
|
def strip(self, data):
|
|
"""
|
|
Strip a HTML string.
|
|
"""
|
|
p = re.compile(r'<.*?>')
|
|
return p.sub(' ', data).strip()
|
|
|
|
|
|
class RawParser(IParser):
|
|
def parse(self, data, encoding=None):
|
|
return data.read()
|
|
|
|
def tostring(self, elem):
|
|
return elem
|